© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107752
    Prev
    Next
    INDEX
    Explanations

    numeric expressions and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    linger
    -0.07
     Ca
    -0.06
    AVED
    -0.06
     Meh
    -0.06
    cbc
    -0.06
     fabric
    -0.06
    aub
    -0.06
     Sok
    -0.06
    avenport
    -0.06
    ETS
    -0.06
    POSITIVE LOGITS
    201
    0.13
    202
    0.13
    Û²Û°Û±
    0.08
    bul
    0.07
    200
    0.07
    ska
    0.07
    heim
    0.07
    ello
    0.07
    exo
    0.07
    iento
    0.07
    Activations Density 0.020%

    No Known Activations